Back to directory

LumiBot

A Python trading framework that runs AI agents or hand-written rule-based strategies through the same backtest-then-broker lifecycle, across twelve broker integrations covering stocks, options, futures, forex, crypto and prediction markets.

LumiBot

LumiBot is a Python algorithmic-trading framework built around a single Strategy lifecycle that can be driven by AI agents, hand-written rules, or both. Unlike a plain trading demo, it is built to actually place orders: a deterministic Python gate sits between a model's decisions and the broker, so trades are backed by real broker integrations rather than only recommendations.

A project is scaffolded with an editable Strategy subclass, backtested on free daily data, and then run against a broker in paper or live mode. It supports twelve broker integrations across stocks, options, futures, forex, crypto and prediction markets, and lets a strategy's logic be reused across different brokers by keeping strategy code separate from broker configuration.

It installs as a Python package and includes a one-command demo backtest that needs no API key or broker account.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.